GLM-4.7 vs Kimi K2.5
Wins 0 of 7 areas
—
Wins 6 of 7 areas
Coding · Agents · Reasoning · Facts · Long documents · Following instructions
Kimi K2.5 is the stronger all-rounder.GLM-4.7 is cheaper.
Scores updated · 43 tests both models report · How we compare
Where each one wins
Tests won in each of the seven areas where both have results. Each piece is one test, so a longer bar means more evidence; grey means the two scored within a point of each other.
- CodingWriting and fixing software04Kimi K2.54 of 7 tests · 3 ties
- ReasoningHard problems that need careful thinking03Kimi K2.53 of 3 tests
- FactsGetting facts right instead of making them up13Kimi K2.53 of 4 tests
- AgentsCarrying out multi-step tasks on its own12Kimi K2.52 of 3 tests
- Long documentsFinding answers in very long texts01Kimi K2.51 of 1 test
- Following instructionsDoing exactly what it is asked01Kimi K2.51 of 1 test
- MathCompetition and research-level math00Even0 each · 1 tie
Math, long documents and following instructions rest on a single test each.
What it costs
Prices per million tokens, roughly 750,000 words. The bars show the cost of a million tokens read plus a million written.
GLM-4.7 costs 22% less for the same work.
The biggest differences
The tests each model wins by the widest margin, up to three each. Scores are out of 100.
Where Kimi K2.5 pulls ahead
- Avoids making up answers it doesn't knowAA-Omniscience · Non-hallucination+27.3points ahead
- Finds hard-to-locate facts by browsing the webBrowseComp+22.9points ahead
- Reasons across sets of long documentsAA-LCR+7points ahead
Where GLM-4.7 pulls ahead
- Real work tasks from 44 professionsGDPVal+8.6points ahead
Every test, side by side
All 43 tests both models report. The winning score is in its model's colour; marks a score checked independently.
CodingKimi K2.5
- SWE-bench MultilingualKimi K2.5 by 6.366.773+6.3
- SciCodeKimi K2.5 by 3.945.149+3.9
- SWE-bench VerifiedKimi K2.5 by 373.876.8+3
- Terminal-Bench HardKimi K2.5 by 331.834.8+3
- Terminal-Bench 2.1tie45.345.7tie
- LiveCodeBench v6tie84.985tie
- LMArena · WebDevtie14351436tie
AgentsKimi K2.5
- BrowseCompKimi K2.5 by 22.95274.9+22.9
- GDPValGLM-4.7 by 8.625.817.2+8.6
- τ-Bench V3 · BankingKimi K2.5 by 212.214.2+2
ReasoningKimi K2.5
- Humanity's Last ExamKimi K2.5 by 3.327.430.7+3.3
- GPQA DiamondKimi K2.5 by 285.987.9+2
- CritPtKimi K2.5 by 1.41.73.1+1.4
FactsKimi K2.5
- AA-Omniscience · Non-hallucinationKimi K2.5 by 27.3734.3+27.3
- AA-Omniscience · AccuracyKimi K2.5 by 5.929.335.2+5.9
- Vectara HHEM hallucination ratelower is betterGLM-4.7 by 2.511.714.2+2.5
- SimpleQA VerifiedKimi K2.5 by 2.132.234.3+2.1
Following instructionsKimi K2.5
- IFBenchKimi K2.5 by 2.367.970.2+2.3
Other results23 tests, not counted
Tests outside the eight areas. They are not counted above: several are summary scores built from other tests, or the same test under another name.
- AA-OmniscienceKimi K2.5 by 29.1-36.4-7.3+29.1
- xbench-DeepSearchKimi K2.5 by 24.452.376.7+24.4
- CyberGymKimi K2.5 by 17.823.541.3+17.8
- GAIA (no file)Kimi K2.5 by 1461.975.9+14
- Terminal-Bench 2.0Kimi K2.5 by 9.84150.8+9.8
- vectara_answer_rateGLM-4.7 by 7.699.892.2+7.6
- browsecomp_with_context_managerKimi K2.5 by 7.467.574.9+7.4
- HLE (with tools)Kimi K2.5 by 7.442.850.2+7.4
- AA Agentic IndexGLM-4.7 by 4.526.221.7+4.5
- BrowseComp-ZHGLM-4.7 by 4.366.662.3+4.3
- HMMT Nov. 2025GLM-4.7 by 4.393.589.2+4.3
- frontiermath_tier_4_v1Kimi K2.5 by 4.204.2+4.2
- vectara_avg_summary_lengthKimi K2.5 by 41.4 rating points70.6112+41.4 rating
- MMLU-ProKimi K2.5 by 2.884.387.1+2.8
- ResearchRubricsGLM-4.7 by 2.56259.5+2.5
- vectara_factual_consistencyGLM-4.7 by 2.588.385.8+2.5
- τ²-BenchGLM-4.7 by 287.485.4+2
- HMMT Feb. 2025GLM-4.7 by 1.797.195.4+1.7
- Artificial Analysis Coding IndexKimi K2.5 by 1.545.346.8+1.5
- AA IntelligenceKimi K2.5 by 1.322.223.5+1.3
- AIME 2025tie95.796.1tie
- AIME 2026 I (Tools-allowed)tie92.992.5tie
- τ²-Bench Telecom (AA run)tie95.995.9tie
Questions people ask
Which is better, GLM-4.7 or Kimi K2.5?
Kimi K2.5 wins six of the seven areas where both have results: coding, agents, reasoning, facts, long documents and following instructions. GLM-4.7 wins none, but costs 22% less. They are level on math.
Which is better for coding?
Kimi K2.5. It wins 4 of the 7 coding tests both models report; GLM-4.7 wins none, and 3 are ties.
Which is cheaper?
GLM-4.7 costs $0.60 per million input tokens and $2.20 per million output tokens; Kimi K2.5 costs $0.60 and $3.00. That makes GLM-4.7 about 22% cheaper for the same work.
How do you compare the two?
We use the 43 benchmark tests both models have published scores on. The verdict counts the 20 tests in the eight capability areas, and a gap under one point (ten on rating-style scales) counts as a tie. The other 23 are listed but not counted, because several are summary scores or repeat a test. Each score is the one shown on the model's own page.